User-agent: *
Allow: /
# Generation-on-miss + personal pages — keep crawlers out (also noindex'd).
Disallow: /search
Disallow: /user

# AI *training* crawlers: ingest content but send no traffic back, and can
# reproduce our snark voice without attribution. Blocked. The search/answer
# bots that CITE + link back (Googlebot, Bingbot, OAI-SearchBot, ChatGPT-User,
# PerplexityBot, Applebot…) are intentionally NOT here — they stay allowed by
# the catch-all above.
# Note: Google-Extended is the Gemini-training token only; blocking it does NOT
# affect Google Search ranking or AI Overviews. robots.txt is advisory — the
# reputable AI companies honor it; enforce at the edge (Cloudflare) for teeth.
User-agent: GPTBot
User-agent: ClaudeBot
User-agent: anthropic-ai
User-agent: Claude-Web
User-agent: CCBot
User-agent: Google-Extended
User-agent: Applebot-Extended
User-agent: Bytespider
User-agent: Meta-ExternalAgent
User-agent: meta-externalagent
User-agent: FacebookBot
User-agent: Amazonbot
User-agent: Diffbot
User-agent: Omgilibot
User-agent: PetalBot
Disallow: /

# SEO / backlink scrapers: they crawl every HTML page for their own commercial
# link indexes, send us zero traffic, and drive real SSR load (a factor in the
# artbot-web memory spikes). Blocked. Search engines that actually send visitors
# (Googlebot, Bingbot, DuckDuckBot…) stay allowed by the catch-all above.
User-agent: AhrefsBot
User-agent: SemrushBot
User-agent: MJ12bot
User-agent: DotBot
User-agent: DataForSeoBot
User-agent: BLEXBot
User-agent: rogerbot
User-agent: Barkrowler
User-agent: SeekportBot
Disallow: /

Sitemap: https://artbot.directory/sitemap.xml